{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/2505-11493","title":"GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing","arxiv_id":"2505.11493","date":"2025-05-16","proceeding":null,"authors":["Yusu Qian","Jiasen Lu","Tsu-Jui Fu","Xinze Wang","Chen Chen","Yinfei Yang","Wenze Hu","Zhe Gan"],"abstract":"Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evaluation approaches often rely on image-text similarity metrics like CLIP, which lack precision. In this work, we introduce a new benchmark designed to evaluate text-guided image editing models in a more grounded manner, along two critical dimensions: (i) functional correctness, assessed via automatically generated multiple-choice questions that verify whether the intended change was successfully applied; and (ii) image content preservation, which ensures that non-targeted regions of the image remain visually consistent using an object-aware masking technique and preservation scoring. The benchmark includes over 1000 high-quality editing examples across 20 diverse content categories, each annotated with detailed editing instructions, evaluation questions, and spatial object masks. We conduct a large-scale study comparing GPT-Image-1, the latest flagship in the text-guided image editing space, against several state-of-the-art editing models, and validate our automatic metrics against human ratings. Results show that GPT-Image-1 leads in instruction-following accuracy, but often over-modifies irrelevant image regions, highlighting a key trade-off in the current model behavior. GIE-Bench provides a scalable, reproducible framework for advancing more accurate evaluation of text-guided image editing.","url_abs":"https://arxiv.org/abs/2505.11493v1","url_pdf":"https://arxiv.org/pdf/2505.11493v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"2505-11493","repo_url":"https://github.com/apple/ml-gie-bench","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"text-similarity","task_name":"text similarity"},{"task_slug":"text-guided-image-editing","task_name":"text-guided-image-editing"}],"methods":[],"datasets_introduced":[{"slug":"gie-bench","name":"GIE-Bench","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.11493","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}